Github user massie commented on a diff in the pull request:
https://github.com/apache/spark/pull/6423#discussion_r31260122
--- Diff:
core/src/main/scala/org/apache/spark/shuffle/hash/HashShuffleReader.scala ---
@@ -33,11 +33,34 @@ private[spark] class HashShuffleReader[K, C](
"Hash shuffle currently only supports fetching one partition")
private val dep = handle.dependency
+ private val blockManager = SparkEnv.get.blockManager
/** Read the combined key-values for this reduce task */
override def read(): Iterator[Product2[K, C]] = {
+ val blockStreams = BlockStoreShuffleFetcher.fetchBlockStreams(
+ handle.shuffleId, startPartition, context)
+
+ // Wrap the streams for compression based on configuration
+ val wrappedStreams = blockStreams.map { case (blockId, inputStream) =>
+ blockManager.wrapForCompression(blockId, inputStream)
+ }
+
val ser = Serializer.getSerializer(dep.serializer)
- val iter = BlockStoreShuffleFetcher.fetch(handle.shuffleId,
startPartition, context, ser)
+ val serializerInstance = ser.newInstance()
+
+ // Create a key/value iterator for each stream
+ val recordIterator = wrappedStreams.flatMap { wrappedStream =>
+
serializerInstance.deserializeStream(wrappedStream).asKeyValueIterator
+ }
+
+ // Update read metrics for each record materialized
+ val iter = new InterruptibleIterator[Any](context, recordIterator) {
+ val readMetrics =
context.taskMetrics.createShuffleReadMetricsForDependency()
+ override def next(): Any = {
+ readMetrics.incRecordsRead(1)
+ delegate.next()
+ }
+ }.asInstanceOf[Iterator[Nothing]]
--- End diff --
This `asInstanceOf` is necessary but ugly. The alternative, I believe,
would be to move this into a method with a generic type, e.g...
```
def newInterruptibleIterator[T](context: ..., completionIter: ...) = {
new InterruptibleIterator[T](context, completionIter) {
val readMetrics =
context.taskMetrics.createShuffleReadMetricsForDependency()
override def next(): T = {
readMetrics.incRecordsRead(1)
delegate.next()
}
}
```
Let me know which approach you prefer.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
